Publications

An improved column-generation-based matheuristic for learning classification trees
Krunal Kishor Patel
Guy Desaulniers
Andrea Lodi
2024-01-01
Comput. Oper. Res. (publié)
doi.org
arxiv.org
An Improved Neuro-Symbolic Architecture to Fine-Tune Generative AI Systems
Chao Yin
Quentin Cappart
Gilles Pesant
2024-01-01
Integration of AI and OR Techniques in Constraint Programming (publié)
doi.org
Improving Adversarial Robustness in Vision-Language Models with Architecture and Prompt Design.
Rishika Bhagwatkar
Shravan Nayak
Pouya Bashivan
Irina Rish
2024-01-01
EMNLP (Findings) (publié)
doi.org
Improving the Generalizability and Robustness of Large-Scale Traffic Signal Control
Tianyu Shi
François-Xavier Devailly
Denis Larocque
Laurent Charlin
A number of deep reinforcement-learning (RL) approaches propose to control traffic signals. Compared to traditional approaches, RL approache… (voir plus)s can learn from higher-dimensionality input road and vehicle sensors and better adapt to varying traffic conditions resulting in reduced travel times (in simulation). However, these RL methods require training from massive traffic sensor data. To offset this relative inefficiency, some recent RL methods have the ability to first learn from small-scale networks and then generalize to unseen city-scale networks without additional retraining (zero-shot transfer). In this work, we study the robustness of such methods along two axes. First, sensor failures and GPS occlusions create missing-data challenges and we show that recent methods remain brittle in the face of these missing data. Second, we provide a more systematic study of the generalization ability of RL methods to new networks with different traffic regimes. Again, we identify the limitations of recent approaches. We then propose using a combination of distributional and vanilla reinforcement learning through a policy ensemble. Building upon the state-of-the-art previous model which uses a decentralized approach for large-scale traffic signal control with graph convolutional networks (GCNs), we first learn models using a distributional reinforcement learning (DisRL) approach. In particular, we use implicit quantile networks (IQN) to model the state-action return distribution with quantile regression. For traffic signal control problems, an ensemble of standard RL and DisRL yields superior performance across different scenarios, including different levels of missing sensor data and traffic flow patterns. Furthermore, the learning scheme of the resulting model can improve zero-shot transferability to different road network structures, including both synthetic networks and real-world networks (e.g., Luxembourg, Manhattan). We conduct extensive experiments to compare our approach to multi-agent reinforcement learning and traditional transportation approaches. Results show that the proposed method improves robustness and generalizability in the face of missing data, varying road networks, and traffic flows.
2024-01-01
IEEE Open Journal of Intelligent Transportation Systems (publié)
doi.org
arxiv.org
Inertia-Based Indices to Determine the Number of Clusters in K-Means: An Experimental Evaluation
Andrei Rykov
Renato Cordeiro De Amorim
Vladimir Makarenkov
Boris Mirkin
This paper gives an experimentally supported review and comparison of several indices based on the conventional K-means inertia criterion fo… (voir plus)r determining the number of clusters,
2024-01-01
IEEE Access (publié)
doi.org
Inertia-Based Indices to Determine the Number of Clusters in K-Means: An Experimental Evaluation
Andrei Rykov
Renato Cordeiro De Amorim
Vladimir Makarenkov
Boris Mirkin
This paper gives an experimentally supported review and comparison of several indices based on the conventional K-means inertia criterion fo… (voir plus)r determining the number of clusters,
2024-01-01
IEEE Access (publié)
doi.org
Inertia-Based Indices to Determine the Number of Clusters in K-Means: An Experimental Evaluation
Andrei Rykov
Renato Cordeiro De Amorim
Vladimir Makarenkov
Boris Mirkin
This paper gives an experimentally supported review and comparison of several indices based on the conventional K-means inertia criterion fo… (voir plus)r determining the number of clusters,
2024-01-01
IEEE Access (publié)
doi.org
Inertia-Based Indices to Determine the Number of Clusters in K-Means: An Experimental Evaluation
Andrei Rykov
Renato Cordeiro De Amorim
Vladimir Makarenkov
Boris Mirkin
This paper gives an experimentally supported review and comparison of several indices based on the conventional K-means inertia criterion fo… (voir plus)r determining the number of clusters,
2024-01-01
IEEE Access (publié)
doi.org
Information Complexity of Stochastic Convex Optimization: Applications to Generalization, Memorization, and Tracing
Idan Attias
Gintare Karolina Dziugaite
MAHDI HAGHIFAM
Roi Livni
Daniel M. Roy
In this work, we investigate the interplay between memorization and learning in the context of stochastic convex optimization (SCO)… (voir plus). We define memorization via the information a learning algorithm reveals about its training data points. We then quantify this information using the framework of conditional mutual information (CMI) proposed by Steinke and Zakynthinou (2020). Our main result is a precise characterization of the tradeoff between the accuracy of a learning algorithm and its CMI, answering an open question posed by Livni (2023). We show that, in the
2024-01-01
International Conference on Machine Learning (publié)
proceedings.mlr.press
Interacting with a Visuotactile Countertop
M. Jenkin
Francois Hogan
Kaleem Siddiqi
Jean-François Tremblay
Bobak H. Baghi
Gregory Dudek
2024-01-01
International Conference on Robotics, Computer Vision and Intelligent Systems (publié)
doi.org
INTREPPPID - An Orthologue-Informed Quintuplet Network for Cross-Species Prediction of Protein-Protein Interaction
Joseph Szymborski
Amin Emad
An overwhelming majority of protein-protein interaction (PPI) studies are conducted in a select few model organisms largely due to constrain… (voir plus)ts in time and cost of the associated “wet lab” experiments. In silico PPI inference methods are ideal tools to overcome these limitations, but often struggle with cross-species predictions. We present INTREPPPID, a method which incorporates orthology data using a new “quintuplet” neural network, which is constructed with five parallel encoders with shared parameters. INTREPPPID incorporates both a PPI classification task and an orthologous locality task. The latter learns embeddings of orthologues that have small Euclidean distances between them and large distances between embeddings of all other proteins. INTREPPPID outperforms all other leading PPI inference methods tested on both the intra-species and cross-species tasks using strict evaluation datasets. We show that INTREPPPID’s orthologous locality loss increases performance because of the biological relevance of the orthologue data, and not due to some other specious aspect of the architecture. Finally, we introduce PPI.bio and PPI Origami, a web server interface for INTREPPPID and a software tool for creating strict evaluation datasets, respectively. Together, these two initiatives aim to make both the use and development of PPI inference tools more accessible to the community. GRAPHICAL ABSTRACT
2024-01-01
Briefings Bioinform. (publié)
doi.org
INViTE: INterpret and Control Vision-Language Models with Text Explanations
Haozhe Chen
Junfeng Yang
Carl Vondrick
Chengzhi Mao
Columbia University
M. University
Large-scale pre-trained vision foundation models, such as CLIP, have become de facto backbones for various vision tasks. However, due to the… (voir plus)ir black-box nature, understanding the underlying rules behind these models’ predictions and controlling model behaviors have remained open challenges. We present INViTE: a framework for INterpreting Vision Transformer’s latent tokens with Text Explanations. Given a latent token, INViTE retains its semantic information to the final layer using transformer’s local operations and retrieves the closest text for explanation. INViTE enables understanding of model visual reasoning procedure without needing additional model training or data collection. Based on the obtained interpretations, INViTE allows for model editing that controls model reasoning behaviors and improves model robustness against biases and spurious correlations. Our code is available at https://github.com/tonychenxyz/vit-interpret.
2024-01-01
International Conference on Learning Representations (publié)
openreview.net
openreview.net